Improving Query Graph Generation for Complex Question Answering over Knowledge Base

Kechen Qin, Cheng Li, Virgil Pavlu, Javed Aslam


Abstract
Most of the existing Knowledge-based Question Answering (KBQA) methods first learn to map the given question to a query graph, and then convert the graph to an executable query to find the answer. The query graph is typically expanded progressively from the topic entity based on a sequence prediction model. In this paper, we propose a new solution to query graph generation that works in the opposite manner: we start with the entire knowledge base and gradually shrink it to the desired query graph. This approach improves both the efficiency and the accuracy of query graph generation, especially for complex multi-hop questions. Experimental results show that our method achieves state-of-the-art performance on ComplexWebQuestion (CWQ) dataset.
Anthology ID:
2021.emnlp-main.346
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4201–4207
Language:
URL:
https://aclanthology.org/2021.emnlp-main.346
DOI:
10.18653/v1/2021.emnlp-main.346
Bibkey:
Cite (ACL):
Kechen Qin, Cheng Li, Virgil Pavlu, and Javed Aslam. 2021. Improving Query Graph Generation for Complex Question Answering over Knowledge Base. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4201–4207, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Improving Query Graph Generation for Complex Question Answering over Knowledge Base (Qin et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.346.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.346.mp4
Data
SimpleQuestions